JP2000306094A - Image processor, image processing method and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately separate an area or symbol solidly painted out in a specified color from an image of a printed matter or the like drawn in plural colors. SOLUTION: A specified color designating part 2 designates a color used for emphasizing processing to an inputted color image. In an emphasizing processing part 2, image data are emphasized by performing prescribed weighting to the respective color components of the image data and an area extracting part 4 for specified color extracts the designated specified color from the emphasized image. In a monochromatic processing part 5, the area in the extracted specified color is converted to a monochromatic gradation image and outputted to an image output part 6.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image processing method and apparatus for extracting a region of a specific color from a color image such as a drawing expressed in a plurality of colors, and a recording medium storing an image processing program.

[0002]

2. Description of the Related Art The present applicant has previously proposed an image recognition method for accurately recognizing outlines of a drawing (for example, walls of a construction drawing) and dividing lines of a table (for example, ruled lines of a form) (Japanese Patent Application Laid-Open No. Hei 8 (1994)). -221571).

[0003] By the way, drawings generally used in the construction / equipment industry or the like are described with a plurality of pieces of information in different colors, or are described or printed on colored paper with a pen different from the paper color. . Alternatively, if a drawing includes a sign on a map, the mark is often composed of a plurality of colors, such as being described in a color scheme substantially matching the primary color of the sign.

[0004]

However, the method proposed above does not deal with color images. Therefore, in the present invention, a pre-processing for accurately recognizing a color image is taken into consideration, and an object of the present invention is to provide a solid-colored area or symbol from an image such as a printed matter drawn in a plurality of colors. Image processing method that separates color by color accurately
A device and a recording medium are provided.

[0005]

In order to achieve the above object, according to the present invention, for a color image input from an image input unit, a color to be emphasized in a specific color designating unit is designated, and an emphasis processing unit is designated. Then, the image data is emphasized by performing predetermined weighting on each color component of the color image data, and the specific color region extracting unit extracts a region of the specified specific color from the emphasized image, and One feature of the conversion processing unit is that the extracted specific color region is converted into a monochrome gradation image and output.

[0006]

DESCRIPTION OF THE PREFERRED EMBODIMENTS One embodiment of the present invention will be specifically described below with reference to the drawings. FIG. 1 shows the configuration of an embodiment of the present invention. In FIG. 1, 1 is an image input unit such as a scanner, 2 is a specific color designation unit, 3 is an enhancement processing unit, 4 is a specific color region extraction unit, 5 is a monochrome processing unit, and 6 is an image output unit such as a display device. Department. FIG. 2 is a processing flowchart of the present invention.

Hereinafter, the processing operation of the present invention will be described by taking as an example the case where a traffic sign is input as a color image. FIG.
Shows the original image of the traffic sign entered in the construction drawing. The symbol portion of the sign has a blue center and a red surrounding. In this traffic sign, the color distribution and the density are adjusted so as to stand out in view of human visual function (sensitivity), that is, when the RGB components are in the ratio of 3: 6: 1. Often.

When red and yellow are extracted from the traffic sign shown in FIG. 3, the following processing is performed. Red and yellow are designated from the specific color designation section 2. The emphasis processing unit 2 emphasizes the image data by weighting each color component of the color image data at 3: 6: 1 (step 102). For example, an input color image is quantized by 8 bits, and R = 5
When 0, G = 100, and B = 60, the R, G, and B values after the enhancement processing are R = 50 × 0.3, G = 100 × 0.
6, B = 60 × 0.1.

Next, the specific color region extracting section 4 extracts a specified specific color region from the emphasized image (step 103). Since yellow is (red + green), R = 50 ×
0.3 is extracted. Also, as yellow, R + G = 50
× 0.3 + 100 × 0.6 is extracted.

Then, the monochrome processing section 5 converts the extracted specific color into a monochrome gradation image and outputs it to the image output section 6 (step 104). Red and yellow are converted to monochrome by the following equation.

A monochrome image = $ 50 × 0.3 + (50 ×
0.3 + 100 × 0.6)｝ / ｛(256 × 0.3) +
(256 × 0.3) + (256 × 0.6)｝.

FIG. 4 shows a display example of image data obtained by extracting red and yellow from the color image of FIG. As shown in the figure, red and yellow (displayed in monochrome in the figure) are extracted with high accuracy. FIG. 5 shows a display example of image data obtained by extracting red and yellow without performing the emphasis processing. It can be seen that the accuracy of red color extraction is lower than in FIG.

FIG. 6 shows the relationship between the color image of FIG.
A display example of image data in which blue and cyan colors (blue + green) are extracted by emphasizing with a weight of G: B = 1: 6: 3 is shown. FIG. 7 shows a display example of image data in which blue and cyan colors are extracted without emphasizing processing. The extraction accuracy of blue is lower than that in FIG.

FIG. 8 shows an example of an image in which a construction drawing is written on light blue graph paper. In the case of recognizing such a wall of a construction drawing using the image recognition method of the above-mentioned publication, the recognition accuracy is improved by removing the light blue background in advance.

Therefore, for the image of FIG. 8, R: G: B
After emphasizing with a weight of = 1: 6: 3, blue (light blue) is removed. FIG. 9 shows an image from which the light blue background has been removed. FIG. 10 shows the result of recognizing the wall of the image of FIG. 9 using, for example, the image recognition method of the above-mentioned publication.

In the above-described embodiment, an example in which an image converted to monochrome is displayed is described. However, by inputting a monochrome image to the feature extraction unit, the outline shape can be extracted and recognized. It is possible.

The weight of R: G: B is not limited to the above example, but R: G: B = α: β: γ (where α + β +
It is sufficient that γ = 1).

The present invention is not limited to the above embodiment, but can be realized by software. When the present invention is implemented by software, as shown in FIG. 11, a CPU, a memory, a display device, a hard disk,
A computer system including a keyboard, a CD-ROM drive, a scanner and the like is prepared, and a computer-readable recording medium such as a CD-ROM stores a program for realizing the function of extracting a region of a specific color of the present invention. Install this program on your system. A color image input from an image input unit such as a scanner is temporarily stored in a hard disk or the like. Then, when the program is started, the temporarily stored image data is read, and a process of emphasizing the specified specific color and extracting a region of the emphasized specific color is executed. Is output to a display or the like.

[0019]

As described above, according to the present invention, an area of a specific color can be accurately extracted from an image composed of a plurality of colors. The recognition rate can be improved. Further, when recognizing the outline of the drawing, unnecessary colors are extracted and removed in advance, so that the recognition can be performed with high accuracy. Further, the contour shape can be smoothly extracted around the boundary portion of the same color region.

[Brief description of the drawings]

FIG. 1 shows a configuration of an embodiment of the present invention.

FIG. 2 shows a processing flowchart of the present invention.

FIG. 3 shows an example of an input color image.

FIG. 4 shows a display example of image data obtained by extracting red and yellow from the color image of FIG.

FIG. 5 shows a display example of image data obtained by performing red and yellow extraction processing without performing the enhancement processing according to the present invention.

6 shows a display example of image data obtained by extracting blue and cyan colors from the color image of FIG.

FIG. 7 shows a display example of image data in which blue and cyan colors are extracted without performing the enhancement processing according to the present invention.

FIG. 8 shows an example of an image in which a construction drawing is written on light blue graph paper.

FIG. 9 shows an image from which the light blue background has been removed.

FIG. 10 shows a result of recognizing a wall in the image of FIG. 9;

FIG. 11 shows a configuration example when the present invention is realized by software.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Image input part 2 Specific color designation part 3 Emphasis processing part 4 Specific color area extraction part 5 Monochrome conversion part 6 Image output part

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) H04N 1/40 D 1/46 Z (72) Inventor Fumihiro Hasegawa 1-3-6 Nakamagome, Ota-ku, Tokyo No. Inside Ricoh Co., Ltd. (72) Inventor Takayuki Nishimura 1-100 Chiyosui, Tottori City, Tottori Prefecture F-term (reference) 5R050 AA00 BA15 BA17 DA04 DA06 EA06 EA09 EA16 5B057 CA01 CA08 CA12 CA16 CB02 CB06 CB12 CB16 CC03 CE03 CE12 DA08 DB02 DB06 DB09 DC25 5C077 MP08 PP32 PP37 PP51 PQ18 RR02 5C079 HB01 LA02 LA34 LB11 NA00 5L096 AA02 BA08 DA01 EA39 FA15

Claims (5)

[Claims] 2. An image processing method comprising: performing an emphasis process on a specific color of color image data; and extracting a region of the specific color from the color image data. 2. The image processing method according to claim 1, wherein said emphasizing process is a process of performing predetermined weighting on a specific color component. 3. The image processing method according to claim 1, wherein the extracted region of the specific color is converted to monochrome. 4. A means for designating a specific color of color image data, a means for enhancing the designated specific color, a means for extracting a region of the enhanced specific color, and An image processing apparatus, comprising: means for converting a color region to monochrome. 5. A computer-readable program storing a program for causing a computer to implement a function of emphasizing a specified specific color in color image data and a function of extracting a region of the emphasized specific color. recoding media.